Generating colloquial radiology reports with large language models
We find that our translations at the eighth-grade level strike an optimal balance between accuracy and readability. Notably, this corresponds to nationally recognized recommendations for patient-facing health communication. We believe that using this approach to draft patient-accessible reports will benefit patients without significantly increasing the burden on radiologists.
Authors
- Daniel Chow (ORCID: https://orcid.org/0000-0002-2359-7394)
- Robert Hill (ORCID: https://orcid.org/0000-0001-6080-8712)
- Justin Glavis‐Bloom (ORCID: https://orcid.org/0000-0002-4879-1572)
- Hayden Troutt (ORCID: https://orcid.org/0000-0003-1079-007X)
- Cynthia Crystal Tang
- Gillean Cortes (ORCID: https://orcid.org/0000-0003-0387-1736)
- Angellica Gordon
- David Fussell (ORCID: https://orcid.org/0009-0003-0833-9148)
- Charles Li (ORCID: https://orcid.org/0000-0001-7088-6087)
- Nina Mishra
- Rod Tarrago
- J. Zhao (ORCID: https://orcid.org/0009-0002-8480-3988)
- Joshua Wright
- Supriya Nagesh
Institutions
- Amazon (United States) (US)
- University of California, Irvine (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2024-08-23
- DOI
- https://doi.org/10.1093/jamia/ocae223
- Citations
- 13
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.56